submission_id: pawankrd-cosmosrp_v28
developer_uid: PawanOsman
status: inactive
model_repo: PawanKrd/CosmosRP
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<', '>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
timestamp: 2024-07-03T22:33:09+00:00
model_name: pawankrd-cosmosrp_v28
model_group: PawanKrd/CosmosRP
num_battles: 14008
num_wins: 7366
celo_rating: 1206.24
propriety_score: 0.7030680437424058
propriety_total_count: 6584.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: pawankrd-cosmosrp_v28
ineligible_reason: None
language_model: PawanKrd/CosmosRP
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-03
win_ratio: 0.5258423757852656
Resubmit model
Running pipeline stage MKMLizer
Starting job with name pawankrd-cosmosrp-v28-mkmlizer
Waiting for job on pawankrd-cosmosrp-v28-mkmlizer to finish
pawankrd-cosmosrp-v28-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
pawankrd-cosmosrp-v28-mkmlizer: ║ _____ __ __ ║
pawankrd-cosmosrp-v28-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
pawankrd-cosmosrp-v28-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
pawankrd-cosmosrp-v28-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
pawankrd-cosmosrp-v28-mkmlizer: ║ /___/ ║
pawankrd-cosmosrp-v28-mkmlizer: ║ ║
pawankrd-cosmosrp-v28-mkmlizer: ║ Version: 0.8.14 ║
pawankrd-cosmosrp-v28-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
pawankrd-cosmosrp-v28-mkmlizer: ║ https://mk1.ai ║
pawankrd-cosmosrp-v28-mkmlizer: ║ ║
pawankrd-cosmosrp-v28-mkmlizer: ║ The license key for the current software has been verified as ║
pawankrd-cosmosrp-v28-mkmlizer: ║ belonging to: ║
pawankrd-cosmosrp-v28-mkmlizer: ║ ║
pawankrd-cosmosrp-v28-mkmlizer: ║ Chai Research Corp. ║
pawankrd-cosmosrp-v28-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
pawankrd-cosmosrp-v28-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
pawankrd-cosmosrp-v28-mkmlizer: ║ ║
pawankrd-cosmosrp-v28-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
pawankrd-cosmosrp-v28-mkmlizer: Downloaded to shared memory in 66.787s
pawankrd-cosmosrp-v28-mkmlizer: quantizing model to /dev/shm/model_cache
pawankrd-cosmosrp-v28-mkmlizer: Saving flywheel model at /dev/shm/model_cache
pawankrd-cosmosrp-v28-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:05<12:13, 2.54s/it] Loading 0: 4%|▍ | 13/291 [00:05<01:22, 3.38it/s] Loading 0: 8%|▊ | 23/291 [00:05<00:38, 6.94it/s] Loading 0: 11%|█▏ | 33/291 [00:05<00:22, 11.49it/s] Loading 0: 15%|█▍ | 43/291 [00:05<00:14, 17.37it/s] Loading 0: 19%|█▊ | 54/291 [00:05<00:09, 25.33it/s] Loading 0: 22%|██▏ | 64/291 [00:06<00:08, 25.48it/s] Loading 0: 26%|██▌ | 76/291 [00:06<00:06, 34.98it/s] Loading 0: 30%|██▉ | 86/291 [00:06<00:04, 42.26it/s] Loading 0: 33%|███▎ | 96/291 [00:06<00:03, 49.77it/s] Loading 0: 37%|███▋ | 108/291 [00:06<00:02, 61.36it/s] Loading 0: 41%|████ | 118/291 [00:06<00:02, 68.30it/s] Loading 0: 45%|████▍ | 130/291 [00:06<00:02, 78.11it/s] Loading 0: 48%|████▊ | 140/291 [00:06<00:01, 81.77it/s] Loading 0: 52%|█████▏ | 150/291 [00:06<00:01, 83.97it/s] Loading 0: 56%|█████▋ | 164/291 [00:07<00:01, 97.98it/s] Loading 0: 60%|██████ | 175/291 [00:07<00:01, 59.03it/s] Loading 0: 64%|██████▎ | 185/291 [00:07<00:01, 64.68it/s] Loading 0: 67%|██████▋ | 195/291 [00:07<00:01, 69.99it/s] Loading 0: 71%|███████▏ | 208/291 [00:07<00:01, 82.24it/s] Loading 0: 76%|███████▌ | 220/291 [00:07<00:00, 85.91it/s] Loading 0: 79%|███████▉ | 230/291 [00:07<00:00, 84.38it/s] Loading 0: 82%|████████▏ | 240/291 [00:08<00:00, 84.13it/s] Loading 0: 87%|████████▋ | 253/291 [00:08<00:00, 94.34it/s] Loading 0: 91%|█████████ | 265/291 [00:08<00:00, 95.02it/s] Loading 0: 95%|█████████▍| 275/291 [00:08<00:00, 58.07it/s] Loading 0: 98%|█████████▊| 285/291 [00:08<00:00, 63.62it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
pawankrd-cosmosrp-v28-mkmlizer: quantized model in 25.706s
pawankrd-cosmosrp-v28-mkmlizer: Processed model PawanKrd/CosmosRP in 92.494s
pawankrd-cosmosrp-v28-mkmlizer: creating bucket guanaco-mkml-models
pawankrd-cosmosrp-v28-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
pawankrd-cosmosrp-v28-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/pawankrd-cosmosrp-v28
pawankrd-cosmosrp-v28-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v28/special_tokens_map.json
pawankrd-cosmosrp-v28-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v28/config.json
pawankrd-cosmosrp-v28-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v28/tokenizer_config.json
pawankrd-cosmosrp-v28-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/pawankrd-cosmosrp-v28/tokenizer.json
pawankrd-cosmosrp-v28-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/pawankrd-cosmosrp-v28/flywheel_model.0.safetensors
pawankrd-cosmosrp-v28-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
pawankrd-cosmosrp-v28-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
pawankrd-cosmosrp-v28-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v28-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
pawankrd-cosmosrp-v28-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v28-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
pawankrd-cosmosrp-v28-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v28-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
pawankrd-cosmosrp-v28-mkmlizer: warnings.warn(
pawankrd-cosmosrp-v28-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
pawankrd-cosmosrp-v28-mkmlizer: return self.fget.__get__(instance, owner)()
pawankrd-cosmosrp-v28-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
pawankrd-cosmosrp-v28-mkmlizer: Saving duration: 0.438s
pawankrd-cosmosrp-v28-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 27.336s
pawankrd-cosmosrp-v28-mkmlizer: creating bucket guanaco-reward-models
pawankrd-cosmosrp-v28-mkmlizer: Bucket 's3://guanaco-reward-models/' created
pawankrd-cosmosrp-v28-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/pawankrd-cosmosrp-v28_reward
pawankrd-cosmosrp-v28-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v28_reward/tokenizer_config.json
pawankrd-cosmosrp-v28-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/pawankrd-cosmosrp-v28_reward/special_tokens_map.json
pawankrd-cosmosrp-v28-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/pawankrd-cosmosrp-v28_reward/config.json
pawankrd-cosmosrp-v28-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/pawankrd-cosmosrp-v28_reward/vocab.json
pawankrd-cosmosrp-v28-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/pawankrd-cosmosrp-v28_reward/merges.txt
pawankrd-cosmosrp-v28-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/pawankrd-cosmosrp-v28_reward/tokenizer.json
pawankrd-cosmosrp-v28-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/pawankrd-cosmosrp-v28_reward/reward.tensors
Job pawankrd-cosmosrp-v28-mkmlizer completed after 145.06s with status: succeeded
Stopping job with name pawankrd-cosmosrp-v28-mkmlizer
Pipeline stage MKMLizer completed in 145.90s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service pawankrd-cosmosrp-v28
Waiting for inference service pawankrd-cosmosrp-v28 to be ready
Inference service pawankrd-cosmosrp-v28 ready after 30.1708984375s
Pipeline stage ISVCDeployer completed in 36.91s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.962376356124878s
Received healthy response to inference request in 1.3541600704193115s
Received healthy response to inference request in 1.3295300006866455s
Received healthy response to inference request in 1.294703722000122s
Received healthy response to inference request in 1.3232028484344482s
5 requests
0 failed requests
5th percentile: 1.3004035472869873
10th percentile: 1.3061033725738525
20th percentile: 1.317503023147583
30th percentile: 1.3244682788848876
40th percentile: 1.3269991397857666
50th percentile: 1.3295300006866455
60th percentile: 1.339382028579712
70th percentile: 1.3492340564727783
80th percentile: 1.475803327560425
90th percentile: 1.7190898418426515
95th percentile: 1.8407330989837645
99th percentile: 1.9380477046966553
mean time: 1.452794599533081
Pipeline stage StressChecker completed in 8.02s
pawankrd-cosmosrp_v28 status is now deployed due to DeploymentManager action
pawankrd-cosmosrp_v28 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics